A Brief Window

I’ve written frequently about permanent job losses caused by artificial intelligence. Wharton professor Ethan Mollick still allows for hope in a recent post. “Misguided companies will see any increase in performance from AI as an excuse to lay off staff, keeping their output the same,” writes Mollick, “More forward-thinking firms will take advantage of these new capabilities to both improve the lives of their employees and expand their own capabilities.”

I have seen no indication of an Ebenezer Scrooge on Christmas morning epiphany by corporate managers. Companies such as Amazon, SpaceX, and Trader Joe’s continue to work actively against employee efforts to organize to improve their lot.

Workers who have balanced their work lives by working from home are increasingly being recalled to the office.

Image by ChatGPT

The reflexive return to maintaining working conditions and pay just slightly above the pain point of employee resignation continues to be the default for most corporate managers.

There is no reason to believe that companies will suddenly become enlightened and let employees improve their lives with the time given back to them by artificial intelligence. Rather, the employees most adept at using the new tools will see that time filled with new assignments transferred from their laid-off colleagues.

There is hope, but the window will close quickly. During the initial AI integration period, employees will gravitate to Mollick’s “forward-thinking firms.” The return of union power could give workers the power to bargain for keeping the reclaimed time for more balanced working conditions.

But if layoffs come rapidly, companies will be able to cherry pick from the unemployed. Unions will fade in the face of worker desperation to keep their jobs. It all depends on the next one to two years. It’s moving that fast.

Re-"Eschering"

Last January, I wrote about changes in this blog to encompass more about STEAM education and Project Based Learning (Ch-Ch-Ch-Ch-Changes! (Sort of).) Now I'm adding something that I've been involved with for more than four years – Artificial Intelligence. I'm a member of AI4CA, a group of California educators developing and promoting AI literacy professional development for K-16 educators.

In that previous post, I used the AI image generator, DALL-E to create images of a school makerspace in the style of artist M.C. Escher. The results were vaguely reminiscent of Escher's work, in a childish sort of way (see left.)

So I decided to give it another shot, with the paid version of ChatGPT. With the current concern about copyright infringement over the materials that companies use to train generative AIs, ChatGPT politely informed me that it could not create an image using the style of living artists. I guess that Escher hasn't been dead long enough. Google's Gemini simply lied to me and denied that it was capable of creating images (it is.)

So I resorted to subterfuge. Here's my dialogue and the resulting images:

Me: "I understand that you cannot create imagery in the style of certain artists. But what would be a good description of the artistic style of M.C. Escher?"

ChatGPT:"M.C. Escher's artistic style is renowned for its intricate detail, mathematical precision, and imaginative use of perspective. Escher's work often explores the concepts of infinity, symmetry, and tessellation, seamlessly blending art and mathematics. He is famous for his impossible constructions, which defy the laws of physical space, creating optical illusions that challenge viewers' perceptions. Escher's art frequently features interlocking geometric patterns that transform into impossible objects or detailed scenes that merge into each other in surprising ways. His use of black and white to create stark contrasts enhances the visual impact of his work, making the impossible seem plausible within the confines of his artistic universe. Escher's unique ability to meld the disciplines of art and science has made his style distinctive and instantly recognizable, appealing to both art aficionados and mathematical enthusiasts alike."

So I reworked the prompt, using ChatGPT's own words against it:

Me: "Please create an image of a school makerspace. The image should feature intricate detail, mathematical precision, and imaginative use of perspective and explore the concepts of infinity, symmetry, and tessellation, seamlessly blending art and mathematics. The image should contain impossible constructions, which defy the laws of physical space, creating optical illusions that challenge viewers' perceptions. Use pen and ink style. Use a cutaway view of the room, showing multiple floors, connected in a way that defies physics."

The result was jaw-dropping.

Image by ChatGPT

This interaction with an AI entity is an example of the sorts of skills that our students will need in the coming AI-infused world. They will need a clear grasp of the problem, sufficient insight into how the tools they will be using work, and the ability to express themselves effectively. The same sorts of skills fostered by Project Based Learning.